Out of 30 samples, we selected 17 for this study. These are the normal tissue samples form the control, the UVA and the UVA+SFN treatment groups. normal tissue samples from the UVB_UA groups as well as tumor samples were excluded from this analysis. Additionally, one of the control samples at Week 2 (baseline) was removed after outlier analysis.
7,219 genes with zero counts in > 80% (> 13 out of 18) of samples were removed. 17,202 out of 24,421 genes were left.
[1] 7219
[1] 17202
Next, we noramized the counts. To convert number of hits to the relative abundane of genes in each sample, we used transcripts per kilobase million (TPM) normalization, which is as following for the j-th sample:
1. normilize for gene length: a[i, j] = 1,000*count[i, j]/gene[i, j] length(bp)
2. normalize for seq depth (i.e. total count): a(i, j)/sum(a[, j])
3. multiply by one million
A very good comparison of normalization techniques can be found at the following video:
RPKM, FPKM and TPM, clearly explained
After the normalization, each sample’s total is 1M:
02w_CON_0 02w_SFN_0 02w_SFN_1 02w_UVB_0 02w_UVB_1 15w_CON_0 15w_CON_1 15w_SFN_0 15w_SFN_1
1e+06 1e+06 1e+06 1e+06 1e+06 1e+06 1e+06 1e+06 1e+06
15w_UVB_0 15w_UVB_1 25w_CON_0 25w_CON_1 25w_SFN_0 25w_SFN_1 25w_UVB_0 25w_UVB_1
1e+06 1e+06 1e+06 1e+06 1e+06 1e+06 1e+06 1e+06
Color Legend:
YELLOW: TMP > 10
RED: TMP > 100
# Separate top 100 abundant genes
tmp <- droplevels(tpm[Geneid %in% levels(tpm$Geneid)[(nrow(tpm) - 99):nrow(tpm)]])
tmp <- melt.data.table(data = tmp,
id.vars = 1:2,
measure.vars = 3:ncol(tmp),
variable.name = "Sample",
value.name = "TPM")
tmp$Week <- substr(x = tmp$Sample,
start = 1,
stop = 3)
tmp$Week <- factor(tmp$Week,
levels = unique(tmp$Week))
tmp$Treatment <- substr(x = tmp$Sample,
start = 5,
stop = 7)
tmp$Treatment <- factor(tmp$Treatment,
levels = c("CON",
"UVB",
"SFN"))
tmp$Replica <- substr(x = tmp$Sample,
start = 9,
stop = 9)
tmp$Replica <- factor(tmp$Replica,
levels = 0:1)
# Plot top 100 abundant genes
p2 <- ggplot(tmp,
aes(x = TPM,
y = Geneid,
fill = Treatment,
shape = Week)) +
# facet_wrap(~ Sex, nrow = 1) +
geom_point(size = 3,
alpha = 0.5) +
geom_vline(xintercept = 1,
linetype = "dashed")
ggplotly(p2)
tmp <- droplevels(tpm[Geneid %in% levels(tpm$Geneid)[1:100]])
tmp <- melt.data.table(data = tmp,
id.vars = 1:2,
measure.vars = 3:ncol(tmp),
variable.name = "Sample",
value.name = "TPM")
tmp$Week <- substr(x = tmp$Sample,
start = 1,
stop = 3)
tmp$Week <- factor(tmp$Week,
levels = unique(tmp$Week))
tmp$Treatment <- substr(x = tmp$Sample,
start = 5,
stop = 7)
tmp$Treatment <- factor(tmp$Treatment,
levels = c("CON",
"UVB",
"SFN"))
tmp$Replica <- substr(x = tmp$Sample,
start = 9,
stop = 9)
tmp$Replica <- factor(tmp$Replica,
levels = 0:1)
# Plot top 100 abundant genes
p3 <- ggplot(tmp,
aes(x = TPM,
y = Geneid,
fill = Treatment,
shape = Week)) +
# facet_wrap(~ Sex, nrow = 1) +
geom_point(size = 3,
alpha = 0.5) +
geom_vline(xintercept = 1,
linetype = "dashed")
ggplotly(p3)
dmeta <- data.table(Sample = colnames(dt1)[-c(1:2)])
dmeta$time <- substr(x = dmeta$Sample,
start = 1,
stop = 3)
dmeta$time <- factor(dmeta$time,
levels = c("02w",
"15w",
"25w"))
dmeta$Week <- factor(dmeta$time,
levels = c("02w",
"15w",
"25w"),
labels = c("Week 2",
"Week 15",
"Week 25"))
dmeta$trt <- substr(x = dmeta$Sample,
start = 5,
stop = 7)
dmeta$trt <- factor(dmeta$trt,
levels = c("CON",
"UVB",
"SFN"))
dmeta$Treatment <- factor(dmeta$trt,
levels = c("CON",
"UVB",
"SFN"),
labels = c("Negative Control",
"Positive Control (UVB)",
"Sulforaphane (SFN)"))
dmeta$Replica <- substr(x = dmeta$Sample,
start = 9,
stop = 9)
dmeta$Replica <- factor(dmeta$Replica,
levels = 0:1)
datatable(dmeta,
rownames = FALSE,
class = "cell-border stripe",
options = list(pageLength = nrow(dmeta)))
NOTE: the distributions are skewed. To make them symmetric, log transformation is often applied. However, there is an issue of zeros. In this instance, we added a small values lambda[i] equal to 1/10 of the smallest non-zero value of i-th gene.
dm.tpm <- as.matrix(tpm[, -c(1:2), with = FALSE])
rownames(dm.tpm) <- tpm$Geneid
# # Remove 02w_CON_1 sample and redo PCA
# dm.tpm <- dm.tpm[, colnames(dm.tpm) != "02w_CON_1"]
# dmeta <- dmeta[dmeta$Sample != "02w_CON_1", ]
# Add lambdas to all values, then take a log
dm.ltpm <- t(apply(X = dm.tpm,
MARGIN = 1,
FUN = function(a) {
lambda <- min(a[a > 0])/10
log(a + lambda)
}))
# PCA----
m1 <- prcomp(t(dm.ltpm),
center = TRUE,
scale. = TRUE)
s1 <- summary(m1)
s1
Importance of components:
PC1 PC2 PC3 PC4 PC5 PC6 PC7
Standard deviation 66.5041 61.8206 45.2845 30.42909 28.24422 26.84136 25.01865
Proportion of Variance 0.2571 0.2222 0.1192 0.05383 0.04637 0.04188 0.03639
Cumulative Proportion 0.2571 0.4793 0.5985 0.65232 0.69869 0.74058 0.77696
PC8 PC9 PC10 PC11 PC12 PC13 PC14
Standard deviation 23.05989 22.08373 21.24391 20.87624 20.6980 20.28169 19.42403
Proportion of Variance 0.03091 0.02835 0.02624 0.02534 0.0249 0.02391 0.02193
Cumulative Proportion 0.80788 0.83623 0.86246 0.88780 0.9127 0.93662 0.95855
PC15 PC16 PC17
Standard deviation 19.14803 18.61200 2.085e-13
Proportion of Variance 0.02131 0.02014 0.000e+00
Cumulative Proportion 0.97986 1.00000 1.000e+00
imp <- data.table(PC = colnames(s1$importance),
Variance = 100*s1$importance[2, ],
Cumulative = 100*s1$importance[3, ])
imp$PC <- factor(imp$PC,
levels = imp$PC)
p1 <- ggplot(imp,
aes(x = PC,
y = Variance)) +
geom_bar(stat = "identity",
fill = "grey",
color = "black") +
geom_line(aes(y = rescale(Cumulative,
to = c(min(Cumulative)*max(imp$Variance)/100,
max(imp$Variance))),
group = rep(1, nrow(imp)))) +
geom_point(aes(y = rescale(Cumulative,
to = c(min(Cumulative)*max(imp$Variance)/100,
max(imp$Variance))))) +
scale_y_continuous("% Variance Explained",
breaks = seq(from = 0,
to = max(imp$Variance),
by = 5),
labels = paste(seq(from = 0,
to = max(imp$Variance),
by = 5),
"%",
sep = ""),
sec.axis = sec_axis(trans = ~.,
name = "% Cumulative Variance",
breaks = seq(from = 0,
to = max(imp$Variance),
length.out = 5),
labels = paste(seq(from = 0,
to = 100,
length.out = 5),
"%",
sep = ""))) +
scale_x_discrete("") +
theme(axis.text.x = element_text(angle = 90,
hjust = 1))
# Save for publication
tiff(filename = "tmp/pca_pareto.tiff",
height = 6,
width = 8,
units = 'in',
res = 600,
compression = "lzw+p")
print(p1)
graphics.off()
print(p1)
# Biplot while keep only the most important variables (Javier)----
# Select PC-s to pliot (PC1 & PC2)
choices <- c(1:3)
# Scores, i.e. points (df.u)
dt.scr <- data.table(m1$x[, choices])
# Add grouping variables
dt.scr$trt <- dmeta$trt
dt.scr$time <- dmeta$time
dt.scr$sample <- dmeta$Sample
# Loadings, i.e. arrows (df.v)
dt.rot <- as.data.frame(m1$rotation[, choices])
dt.rot$feat <- rownames(dt.rot)
dt.rot <- data.table(dt.rot)
# Axis labels
u.axis.labs <- paste(colnames(dt.rot)[choices],
sprintf('(%0.1f%% explained var.)',
100*m1$sdev[choices]^2/sum(m1$sdev^2)))
p1 <- ggplot(data = dt.scr,
aes(x = PC1,
y = PC2,
color = trt,
shape = time)) +
geom_point(size = 4,
alpha = 0.5) +
scale_x_continuous(u.axis.labs[1]) +
scale_y_continuous(u.axis.labs[2]) +
theme(legend.position = "none")
ggplotly(p1)
p2 <- ggplot(data = dt.scr,
aes(x = PC1,
y = PC3,
color = trt,
shape = time)) +
geom_point(size = 4,
alpha = 0.5) +
scale_x_continuous(u.axis.labs[1]) +
scale_y_continuous(u.axis.labs[3]) +
theme(legend.position = "none")
ggplotly(p2)
p3 <- ggplot(data = dt.scr,
aes(x = PC2,
y = PC3,
color = trt,
shape = time)) +
geom_point(size = 4,
alpha = 0.5) +
scale_x_continuous(u.axis.labs[2]) +
scale_y_continuous(u.axis.labs[3]) +
theme(legend.position = "none")
ggplotly(p3)
# Legend only
tmp <- ggplot(data = dt.scr,
aes(x = PC1,
y = PC2,
color = trt,
shape = time)) +
geom_point() +
scale_color_discrete("Treatment") +
scale_shape_discrete("Week")
p4 <- as_ggplot(get_legend(tmp))
# Save for publication
tiff(filename = "tmp/pca.tiff",
height = 7,
width = 9,
units = 'in',
res = 600,
compression = "lzw+p")
grid.arrange(p1, p2, p3, p4,
nrow = 2)
graphics.off()
scatterplot3js(x = dt.scr$PC1,
y = dt.scr$PC2,
z = dt.scr$PC3,
color = as.numeric(dt.scr$trt),
renderer = "auto",
pch = dt.scr$sample,
size = 0.1)
Sources:
1. Analyzing RNA-seq data with DESeq2:Interactions
2. Bioconductor Question: DESeq2 time series analysis
We are testing a model with time*treatment interaction. The idea here is to find genes with significant interaction term. That would suggest that the gene expressiondifferences between the treatments depended on time. THere are several possible scenarios:
a. No difference between the negative control and the positive control groups at baseline, significant difference at the later time point. This will show the effect of the disease (UVB radiation, in this case).
b. Significant difference between the control groups at baseline, no difference at the later time point. Same as (a) above.
c. Differences between the positive control and the SFN-treated groups. Here, we are interested in the reversal of UVB effect. Again, the interaction term will need to be significant for the reasons described above.
# Relevel: make all comparisons with the positive control (UVB)
dmeta$trt <- factor(dmeta$trt,
levels = c("UVB",
"CON",
"SFN"))
dtm<- as.matrix(dt1[, dmeta$Sample,
with = FALSE])
rownames(dtm) <- dt1$Geneid
dds <- DESeqDataSetFromMatrix(countData = dtm,
colData = dmeta,
~ time + trt + time:trt)
# If all samples contain zeros, geometric means cannot be
# estimated. Change default 'type = "ratio"' to 'type = "poscounts"'.
# Type '?DESeq2::estimateSizeFactors' for more details.
dds <- estimateSizeFactors(object = dds,
type = "poscounts")
# Run DESeq----
dds <- DESeq(object = dds,
# test = "LRT",
# reduced = ~ time + trt,
fitType = "local",
sfType = "ratio",
parallel = FALSE)
using pre-existing size factors
estimating dispersions
gene-wise dispersion estimates
mean-dispersion relationship
final dispersion estimates
fitting model and testing
# NOTE (from DESeq help file, section Value):
# A DESeqDataSet object with results stored as metadata columns.
# These results should accessed by calling the results function.
# By default this will return the log2 fold changes and p-values
# for the last variable in the design formula.
# See results for how to access results for other variables.
# In this case, the last term is the interaction term trt:time
# NOTE:
# Likelihood ratio test (LRT) (chi-squared test) for GLM will only return
# the results for the difference between the full and the reduced model
resultsNames(dds)
[1] "Intercept" "time_15w_vs_02w" "time_25w_vs_02w" "trt_CON_vs_UVB"
[5] "trt_SFN_vs_UVB" "time15w.trtCON" "time25w.trtCON" "time15w.trtSFN"
[9] "time25w.trtSFN"
# Model matrix
mm1 <- model.matrix(~ time + trt + time:trt, dmeta)
mm1
(Intercept) time15w time25w trtCON trtSFN time15w:trtCON time25w:trtCON time15w:trtSFN
1 1 0 0 1 0 0 0 0
2 1 0 0 0 1 0 0 0
3 1 0 0 0 1 0 0 0
4 1 0 0 0 0 0 0 0
5 1 0 0 0 0 0 0 0
6 1 1 0 1 0 1 0 0
7 1 1 0 1 0 1 0 0
8 1 1 0 0 1 0 0 1
9 1 1 0 0 1 0 0 1
10 1 1 0 0 0 0 0 0
11 1 1 0 0 0 0 0 0
12 1 0 1 1 0 0 1 0
13 1 0 1 1 0 0 1 0
14 1 0 1 0 1 0 0 0
15 1 0 1 0 1 0 0 0
16 1 0 1 0 0 0 0 0
17 1 0 1 0 0 0 0 0
time25w:trtSFN
1 0
2 0
3 0
4 0
5 0
6 0
7 0
8 0
9 0
10 0
11 0
12 0
13 0
14 1
15 1
16 0
17 0
attr(,"assign")
[1] 0 1 1 2 2 3 3 3 3
attr(,"contrasts")
attr(,"contrasts")$time
[1] "contr.treatment"
attr(,"contrasts")$trt
[1] "contr.treatment"
head(mcols(dds))
DataFrame with 6 rows and 50 columns
baseMean baseVar allZero dispGeneEst dispGeneIter
<numeric> <numeric> <logical> <numeric> <numeric>
Xkr4 0.414423785139076 0.750734393874421 FALSE 1e-08 1
Mrpl15 497.506315418383 6139.21631388383 FALSE 0.00292023552394721 6
Lypla1 1316.42450437205 94053.122870121 FALSE 0.00514177871417793 10
Tcea1 362.833336721312 2447.08771392985 FALSE 1e-08 20
Rgs20 412.785226796461 8337.26279018443 FALSE 0.0222228623148068 8
Atp6v1h 1163.12136188358 26870.2895984056 FALSE 0.00473653527254895 9
dispFit dispersion dispIter dispOutlier dispMAP
<numeric> <numeric> <integer> <logical> <numeric>
Xkr4 2.35686251255345 6.43661011051539 8 FALSE 6.43661011051539
Mrpl15 0.00975181583387631 0.0060101698743299 8 FALSE 0.0060101698743299
Lypla1 0.0074100485818535 0.00604102606581283 9 FALSE 0.00604102606581283
Tcea1 0.0123515065189161 0.00715812241817593 7 FALSE 0.00715812241817593
Rgs20 0.0111228088946145 0.0168637514204584 11 FALSE 0.0168637514204584
Atp6v1h 0.00743062379729061 0.00580961463958366 9 FALSE 0.00580961463958366
Intercept time_15w_vs_02w time_25w_vs_02w trt_CON_vs_UVB
<numeric> <numeric> <numeric> <numeric>
Xkr4 -2.359805612164 -0.228477588168501 -0.165844507463528 0.0598562849180821
Mrpl15 9.06594448953328 -0.137408907813809 -0.0412786898053219 -0.308591258014163
Lypla1 10.7337301130648 -0.629677974788472 -0.599280178188303 -0.305684497430534
Tcea1 8.78214921631808 -0.516217579095005 -0.446190172830842 -0.196562316500229
Rgs20 8.98928399842352 -0.547987096260501 -0.45980987283847 -0.0685634893160301
Atp6v1h 10.4068496272689 -0.491695240290437 -0.365919358337453 -0.17807000833384
trt_SFN_vs_UVB time15w.trtCON time25w.trtCON time15w.trtSFN
<numeric> <numeric> <numeric> <numeric>
Xkr4 1.6582080718198 2.45478731530058 3.43262855563513 -1.67076473658365
Mrpl15 0.199168294921519 0.0156586240981802 -0.102536901707458 -0.178149323759463
Lypla1 0.179718039995711 0.281344903276623 0.348189855674569 -0.107101147581259
Tcea1 -0.0830935380769627 0.309506757416714 0.476511703155704 0.271157924759699
Rgs20 0.113854717310148 -0.0460895727086707 -0.119888249480383 0.24522833856804
Atp6v1h 0.0799789915431519 0.246974241692442 0.3213538709111 0.171814404854682
time25w.trtSFN SE_Intercept SE_time_15w_vs_02w SE_time_25w_vs_02w
<numeric> <numeric> <numeric> <numeric>
Xkr4 -1.57787360996648 2.96284694407196 4.19009832838988 4.19009832833768
Mrpl15 -0.0710688162246861 0.0911721029656416 0.128443851313393 0.12828481198956
Lypla1 -0.0334225250935585 0.0832744171626043 0.118643311639213 0.118734269568226
Tcea1 0.104295727467573 0.0997712835011623 0.143038313778663 0.142999047037131
Rgs20 -0.0021489805803274 0.140429387999271 0.199941844408924 0.199839918784151
Atp6v1h 0.0421037362927887 0.082816070681427 0.117808586333953 0.117641366800501
SE_trt_CON_vs_UVB SE_trt_SFN_vs_UVB SE_time15w.trtCON SE_time25w.trtCON
<numeric> <numeric> <numeric> <numeric>
Xkr4 5.13171132899515 4.17888254775382 6.55361338849756 6.5053324829564
Mrpl15 0.161651924073278 0.128745553404475 0.208065870702812 0.207540172422408
Lypla1 0.145519737526484 0.117738852864755 0.188694868576427 0.188378486771387
Tcea1 0.175595965579231 0.142746566195654 0.228119616478045 0.226530264396902
Rgs20 0.244051721146729 0.198791901404911 0.317398591717306 0.316856976912824
Atp6v1h 0.144448031460997 0.117328387791251 0.187086661574303 0.186409051317023
SE_time15w.trtSFN SE_time25w.trtSFN WaldStatistic_Intercept
<numeric> <numeric> <numeric>
Xkr4 5.91776899533986 5.9177689953029 -0.796465580810876
Mrpl15 0.181401275197653 0.181107411065465 99.437702922678
Lypla1 0.16762877155602 0.167772361896891 128.895889983904
Tcea1 0.202476358816243 0.203686983950883 88.022814863515
Rgs20 0.281821816802482 0.282640507763004 64.012840378327
Atp6v1h 0.16627170341325 0.16643031647693 125.662199880281
WaldStatistic_time_15w_vs_02w WaldStatistic_time_25w_vs_02w
<numeric> <numeric>
Xkr4 -0.0545279776897975 -0.0395800991928805
Mrpl15 -1.06979747499584 -0.321773787287314
Lypla1 -5.30731961278428 -5.0472385130895
Tcea1 -3.6089462009025 -3.12023179227889
Rgs20 -2.74073242587354 -2.30089101134551
Atp6v1h -4.17367914845039 -3.11046503699663
WaldStatistic_trt_CON_vs_UVB WaldStatistic_trt_SFN_vs_UVB
<numeric> <numeric>
Xkr4 0.0116640007749233 0.396806575171895
Mrpl15 -1.90898598815487 1.54699164091361
Lypla1 -2.10063942270993 1.52641235771297
Tcea1 -1.11940109701175 -0.582105337392646
Rgs20 -0.280938355992205 0.572733177284935
Atp6v1h -1.23276175197943 0.681667864434048
WaldStatistic_time15w.trtCON WaldStatistic_time25w.trtCON
<numeric> <numeric>
Xkr4 0.374570053157096 0.527663814974626
Mrpl15 0.075258013461256 -0.494058092516009
Lypla1 1.49100452703975 1.84835254620728
Tcea1 1.35677396882921 2.10352336110292
Rgs20 -0.145210388172487 -0.378367081099077
Atp6v1h 1.32010609208693 1.72391774240929
WaldStatistic_time15w.trtSFN WaldStatistic_time25w.trtSFN WaldPvalue_Intercept
<numeric> <numeric> <numeric>
Xkr4 -0.282330171708181 -0.266633187476376 0.425761473479907
Mrpl15 -0.982073161091917 -0.39241252363216 0
Lypla1 -0.638918644974184 -0.199213533836397 0
Tcea1 1.33920782823731 0.512039235127185 0
Rgs20 0.870153848805504 -0.00760322926581116 0
Atp6v1h 1.03333520573646 0.25298117064282 0
WaldPvalue_time_15w_vs_02w WaldPvalue_time_25w_vs_02w WaldPvalue_trt_CON_vs_UVB
<numeric> <numeric> <numeric>
Xkr4 0.956514518769316 0.968427893548228 0.990693684883985
Mrpl15 0.284710479117951 0.747624073744977 0.0562638992384959
Lypla1 1.11249010699918e-07 4.48241630561262e-07 0.0356726306570048
Tcea1 0.000307443353893709 0.00180708779608543 0.262969063182376
Rgs20 0.00613024072810697 0.0213977923150809 0.778757681035553
Atp6v1h 2.99719777251695e-05 0.00186793007683514 0.217664665159797
WaldPvalue_trt_SFN_vs_UVB WaldPvalue_time15w.trtCON WaldPvalue_time25w.trtCON
<numeric> <numeric> <numeric>
Xkr4 0.691510101678589 0.707980248270468 0.597732692383313
Mrpl15 0.121865261334255 0.940009427107256 0.621265153192805
Lypla1 0.126907201963519 0.135960306359441 0.0645513587969476
Tcea1 0.560495730233128 0.174853041105187 0.0354200453908308
Rgs20 0.566825369916453 0.88454476429304 0.705157919128452
Atp6v1h 0.49544899193699 0.18679959906884 0.0847226938662104
WaldPvalue_time15w.trtSFN WaldPvalue_time25w.trtSFN betaConv betaIter
<numeric> <numeric> <logical> <numeric>
Xkr4 0.777690352523301 0.789751600479958 TRUE 13
Mrpl15 0.326063806588436 0.694753434090283 TRUE 2
Lypla1 0.522875857997676 0.842095713129838 TRUE 2
Tcea1 0.180503024691872 0.608623550427472 TRUE 2
Rgs20 0.384216333175638 0.993933559205863 TRUE 3
Atp6v1h 0.301447057198772 0.800282763673559 TRUE 2
deviance maxCooks
<numeric> <logical>
Xkr4 25.9033824686373 NA
Mrpl15 165.306361397833 NA
Lypla1 196.962147294101 NA
Tcea1 157.679951768679 NA
Rgs20 178.614721232345 NA
Atp6v1h 192.597108944526 NA
# res_con_uvb_week2 <- results(dds,
# contrast = c(0,0,0,1,0,0,0,0,0),
# alpha = 0.1)
# SAME AS:
res_con_uvb_week2 <- results(dds,
name = "trt_CON_vs_UVB",
alpha = 0.1)
res_con_uvb_week2 <- res_con_uvb_week2[order(res_con_uvb_week2$padj,
decreasing = FALSE),]
summary(res_con_uvb_week2)
out of 17202 with nonzero total read count
adjusted p-value < 0.1
LFC > 0 (up) : 1546, 9%
LFC < 0 (down) : 1537, 8.9%
outliers [1] : 0, 0%
low counts [2] : 2335, 14%
(mean count < 2)
[1] see 'cooksCutoff' argument of ?results
[2] see 'independentFiltering' argument of ?results
# How many adjusted p-values were less than 0.05?
sum(res_con_uvb_week2$padj < 0.1,
na.rm = TRUE)
[1] 3083
# MA plot
# Save for publication
tiff(filename = "tmp/ma_w2_con_uvb.tiff",
height = 6,
width = 7,
units = 'in',
res = 600,
compression = "lzw+p")
plotMA(res_con_uvb_week2,
main = "Control vs. UVB at Week 2",
alpha = 0.8)
graphics.off()
plotMA(res_con_uvb_week2,
main = "Control vs. UVB at Week 2",
alpha = 0.8)
# res_sfn_uvb_week2 <- results(dds,
# contrast = c(0,0,0,0,1,0,0,0,0),
# alpha = 0.1)
# SAME AS;
res_sfn_uvb_week2 <- results(dds,
name = "trt_SFN_vs_UVB",
alpha = 0.1)
res_sfn_uvb_week2 <- res_sfn_uvb_week2[order(res_sfn_uvb_week2$padj,
decreasing = FALSE),]
summary(res_sfn_uvb_week2)
out of 17202 with nonzero total read count
adjusted p-value < 0.1
LFC > 0 (up) : 26, 0.15%
LFC < 0 (down) : 35, 0.2%
outliers [1] : 0, 0%
low counts [2] : 3669, 21%
(mean count < 5)
[1] see 'cooksCutoff' argument of ?results
[2] see 'independentFiltering' argument of ?results
# How many adjusted p-values were less than 0.05?
sum(res_sfn_uvb_week2$padj < 0.1,
na.rm = TRUE)
[1] 61
# MA plot
# Save for publication
tiff(filename = "tmp/ma_w2_sfn_uvb.tiff",
height = 6,
width = 7,
units = 'in',
res = 600,
compression = "lzw+p")
print(plotMA(res_sfn_uvb_week2,
main = "UVB+SFN vs UVB at Week 2",
alpha = 0.8))
NULL
graphics.off()
print(plotMA(res_sfn_uvb_week2,
main = "UVB+SFN vs UVB at Week 2",
alpha = 0.8))
NULL
lgene.w2.con <- unique(res_con_uvb_week2@rownames[res_con_uvb_week2$padj < 0.1])
lgene.w2.sfn <- unique(res_sfn_uvb_week2@rownames[res_sfn_uvb_week2$padj < 0.1])
lgene.w2 <- lgene.w2.con[lgene.w2.con %in% lgene.w2.sfn]
lgene.w2 <- lgene.w2 [!is.na(lgene.w2 )]
lgene.w2
[1] "Utrn" "Stom" "Tesc" "Cited4" "Cdhr1" "Slc7a11" "Mki67" "Cyp26b1"
[9] "Smc2" "Mad2l1" "Slc4a7" "Ankrd23" "Ifitm3" "Etv3" "Pla2g4d" "Fetub"
[17] "Kif11" "Ccl6" "Has3" "Il19" "A4galt" "Otud1" "Msn" "Nqo1"
[25] "Dbf4" "Cblb" "Tbc1d24" "Elmo2" "Cd163" "Esd" "Rfx2" "Gsta1"
[33] "Slurp1" "Arntl2" "Vldlr" "Tmem173" "Gpx2" "Slfn9" "Adh7" "Sprr2i"
[41] "Bcl2l15"
Plot of DESeq-normalizedcounts of genes significant in both comparisons at Week 2:
# Get the DESeq-normalize counts
dp1 <- list()
for (i in 1:length(lgene.w2)) {
out <- plotCounts(dds,
gene = lgene.w2[[i]],
intgroup = c("trt",
"time"),
returnData = TRUE)
dp1[[i]] <- data.table(Geneid = lgene.w2[[i]],
Sample = rownames(out),
out)
}
dp1 <- rbindlist(dp1)
dp1$trt <- factor(dp1$trt,
levels = c("CON",
"UVB",
"SFN"))
dp1$time <- factor(dp1$time,
levels = c("02w",
"15w",
"25w"),
labels = c("Week 2",
"Week 15",
"Week 25"))
dp1$Geneid <- factor(dp1$Geneid,
levels = lgene.w2)
dp1[, mu := mean(count,
na.rm = TRUE),
by = c("Geneid",
"trt",
"time")]
dmu <- unique(dp1[, -c("Sample",
"count")])
datatable(head(dmu),
rownames = FALSE,
class = "cell-border stripe") %>%
formatRound(columns = 4,
digits = 2)
List of 1
$ axis.text.x:List of 11
..$ family : NULL
..$ face : NULL
..$ colour : NULL
..$ size : NULL
..$ hjust : num 1
..$ vjust : NULL
..$ angle : num 45
..$ lineheight : NULL
..$ margin : NULL
..$ debug : NULL
..$ inherit.blank: logi FALSE
..- attr(*, "class")= chr [1:2] "element_text" "element"
- attr(*, "class")= chr [1:2] "theme" "gg"
- attr(*, "complete")= logi FALSE
- attr(*, "validate")= logi TRUE
dp1.tmp <- dp1[dp1$Geneid %in% unique(dmu.w2$Geneid[dmu.w2$up.dn]), ]
dmu.tmp <- dmu[dmu$Geneid %in% unique(dmu.w2$Geneid[dmu.w2$up.dn]), ]
p1 <- ggplot(dp1.tmp,
aes(x = time,
y = count,
group = trt,
fill = trt)) +
facet_wrap(~ Geneid,
scale = "free_y") +
geom_point(position = position_dodge(0.5),
shape = 21,
size = 5,
color = "black") +
geom_line(data = dmu.tmp,
aes(x = time,
y = mu,
group = trt,
colour = trt),
position = position_dodge(0.5),
alpha = 0.5,
size = 2) +
scale_x_discrete("") +
scale_y_continuous("DESeq-Normalized Counts") +
scale_fill_discrete("Treatment")
print(p1)
List of 1
$ axis.text.x:List of 11
..$ family : NULL
..$ face : NULL
..$ colour : NULL
..$ size : NULL
..$ hjust : num 1
..$ vjust : NULL
..$ angle : num 45
..$ lineheight : NULL
..$ margin : NULL
..$ debug : NULL
..$ inherit.blank: logi FALSE
..- attr(*, "class")= chr [1:2] "element_text" "element"
- attr(*, "class")= chr [1:2] "theme" "gg"
- attr(*, "complete")= logi FALSE
- attr(*, "validate")= logi TRUE
dp1.tmp <- dp1[dp1$Geneid %in% unique(dmu.w2$Geneid[dmu.w2$dn.up]), ]
dmu.tmp <- dmu[dmu$Geneid %in% unique(dmu.w2$Geneid[dmu.w2$dn.up]), ]
p1 <- ggplot(dp1.tmp,
aes(x = time,
y = count,
group = trt,
fill = trt)) +
facet_wrap(~ Geneid,
scale = "free_y") +
geom_point(position = position_dodge(0.5),
shape = 21,
size = 5,
color = "black") +
geom_line(data = dmu.tmp,
aes(x = time,
y = mu,
group = trt,
colour = trt),
position = position_dodge(0.5),
alpha = 0.5,
size = 2) +
scale_x_discrete("") +
scale_y_continuous("DESeq-Normalized Counts") +
scale_fill_discrete("Treatment")
print(p1)
In many of these genes, UVB+SFN moved closer to UVB over time.
up.dn.w2 <- unique(as.character(dmu.w2$Geneid[dmu.w2$up.dn]))
dn.up.w2 <- unique(as.character(dmu.w2$Geneid[dmu.w2$dn.up]))
ll <- unique(c(up.dn.w2,
dn.up.w2))
# 36 genes
con_uvb_week2 <- data.table(Geneid = res_con_uvb_week2@rownames,
log2FoldChange = res_con_uvb_week2@listData$log2FoldChange)
sfn_uvb_week2 <- data.table(Geneid = res_sfn_uvb_week2@rownames,
log2FoldChange = -res_sfn_uvb_week2@listData$log2FoldChange)
t1 <- merge(con_uvb_week2[con_uvb_week2$Geneid %in% ll, ],
sfn_uvb_week2[sfn_uvb_week2$Geneid %in% ll, ],
by = "Geneid")
colnames(t1)[2:3] <- c("Control vs. UVB",
"UVB vs. SFN+UVB")
t1 <- t1[order(t1$`Control vs. UVB`,
decreasing = TRUE), ]
write.csv(t1,
file = "tmp/w2_sign_changes.csv",
row.names = FALSE)
ll <- melt.data.table(data = t1,
id.vars = 1,
measure.vars = 2:3,
variable.name = "Comparison",
value.name = "Gene Expression Diff")
ll$Comparison <- factor(ll$Comparison,
levels = c("Control vs. UVB",
"UVB vs. SFN+UVB"))
lvls <- ll[ll$Comparison == "Control vs. UVB", ]
ll$Geneid <- factor(ll$Geneid,
levels = lvls$Geneid[order(lvls$`Gene Expression Diff`)])
# Add dendrogram----
dt.dndr <- data.frame(t1[Geneid %in% levels(ll$Geneid), ])
rownames(dt.dndr) <- dt.dndr$Gene
dt.dndr <- dt.dndr[, -1]
# Compute distances between genes----
sampleDists <- dist(dt.dndr)
# Make dendrogram data----
dhc <- as.dendrogram(hclust(d = sampleDists),
horiz = TRUE)
ddata <- dendro_data(dhc,
type = "rectangle")
# Segment data----
dtp1 <- segment(ddata)
# Hitmap data----
dtp2 <- ll
dtp2$Geneid <- factor(dtp2$Geneid,
levels = ddata$labels$label)
offset.size <- 4
p1 <- ggplot(data = dtp2) +
coord_polar("y",
start = -0.3,
direction = -1) +
geom_tile(aes(x = as.numeric(Comparison),
y = Geneid,
fill = `Gene Expression Diff`),
color = "white") +
geom_text(data = dtp2[Comparison == "Control vs. UVB", ],
aes(x = rep(1.75,
nlevels(Geneid)),
y = Geneid,
angle = 90 + seq(from = 30,
to = 330,
length.out = nlevels(Geneid))[as.numeric(Geneid)] +
offset.size,
label = unique(Geneid)),
hjust = 0) +
geom_text(data = dtp2[Geneid == levels(dtp2$Geneid)[1], ],
aes(x = 1:nlevels(Comparison),
y = rep(-offset.size,
nlevels(Comparison)),
angle = 0,
label = levels(Comparison)),
hjust = 1,
size = 5) +
scale_fill_gradient2(low = "red",
high = "green",
mid = "grey",
midpoint = 0,
name = "") +
scale_y_discrete("",
expand = c(0, 0)) +
theme(plot.title = element_text(hjust = 0.5),
axis.title.x = element_blank(),
axis.text.x = element_blank(),
axis.ticks.x = element_blank(),
axis.title.y = element_blank(),
axis.text.y = element_blank(),
axis.ticks.y = element_blank(),
panel.background = element_blank(),
legend.position = "bottom",
legend.text = element_text(size = 15),
legend.direction = "horizontal",
legend.key.width = unit(1, "in"),
legend.key.height = unit(0.3, "in")) +
geom_segment(data = dtp1,
aes(x = -sqrt(y) + 0.5,
y = x,
xend = -sqrt(yend) + 0.5,
yend = xend),
size = 1)
tiff(filename = "tmp/skin_ubv_w2_sfn_hitmap_with_phylo.tiff",
height = 8,
width = 8,
units = 'in',
res = 600,
compression = "lzw+p")
plot(p1)
graphics.off()
print(p1)
# 1. Ctrl vs. UVB
# adjusted p-value < 0.1
# LFC > 0 (up) : 1546, 9%
# LFC < 0 (down) : 1537, 8.9%
# 23 genes down-up-down
# 2. SFN+UVB vs. UVB
# adjusted p-value < 0.1
# LFC > 0 (up) : 26, 0.15%
# LFC < 0 (down) : 35, 0.2%
# 13 gens up-down-up
p1 <- ggplot() +
geom_circle(aes(x0 = c(1, 2, 1, 2),
y0 = c(1, 1, 4, 4),
r = rep(1, 4),
color = factor(c(2, 1, 1, 2))),
size = 2) +
geom_text(aes(x = rep(c(0.5, 1.5, 2.5), 2),
y = rep(c(1, 4), each = 3),
label = format(c(26, 13, 35, 1546, 23, 1537),
big.mark = ","))) +
scale_color_manual(values = c("green", "red")) +
theme_void() +
theme(legend.position = "none")
tiff(filename = "tmp/skin_ubv_sfn_w2_venn.tiff",
height = 6,
width = 4,
units = 'in',
res = 600,
compression = "lzw+p")
plot(p1)
graphics.off()
print(p1)
res_con_uvb_week15 <- results(dds,
contrast = c(0,0,0,1,0,1,0,0,0),
alpha = 0.1)
res_con_uvb_week15 <- res_con_uvb_week15[order(res_con_uvb_week15$padj,
decreasing = FALSE),]
summary(res_con_uvb_week15)
out of 17202 with nonzero total read count
adjusted p-value < 0.1
LFC > 0 (up) : 1513, 8.8%
LFC < 0 (down) : 1463, 8.5%
outliers [1] : 0, 0%
low counts [2] : 2668, 16%
(mean count < 2)
[1] see 'cooksCutoff' argument of ?results
[2] see 'independentFiltering' argument of ?results
# out of 17202 with nonzero total read count
# adjusted p-value < 0.1
# LFC > 0 (up) : 1513, 8.8%
# LFC < 0 (down) : 1463, 8.5%
# outliers [1] : 0, 0%
# low counts [2] : 2668, 16%
# (mean count < 2)
# How many adjusted p-values were less than 0.01?
sum(res_con_uvb_week15$padj < 0.1,
na.rm = TRUE)
[1] 2976
# 2976
# NOT THE SAME AS?!!!:
res_con_uvb_week15.1 <- results(dds,
contrast = list("trt_CON_vs_UVB",
"time15w.trtCON"),
alpha = 0.1)
res_con_uvb_week15.1 <- res_con_uvb_week15.1[order(res_con_uvb_week15.1$padj,
decreasing = FALSE),]
summary(res_con_uvb_week15.1)
out of 17202 with nonzero total read count
adjusted p-value < 0.1
LFC > 0 (up) : 469, 2.7%
LFC < 0 (down) : 455, 2.6%
outliers [1] : 0, 0%
low counts [2] : 4002, 23%
(mean count < 6)
[1] see 'cooksCutoff' argument of ?results
[2] see 'independentFiltering' argument of ?results
# out of 17202 with nonzero total read count
# adjusted p-value < 0.1
# LFC > 0 (up) : 469, 2.7%
# LFC < 0 (down) : 455, 2.6%
# outliers [1] : 0, 0%
# low counts [2] : 4002, 23%
# (mean count < 6)
# How many adjusted p-values were less than 0.01?
sum(res_con_uvb_week15.1$padj < 0.1,
na.rm = TRUE)
[1] 924
# 924
# MA plot
# Save for publication
tiff(filename = "tmp/ma_w15_con_uvb.tiff",
height = 6,
width = 7,
units = 'in',
res = 600,
compression = "lzw+p")
plotMA(res_con_uvb_week15,
main = "Control vs. UVB at Week 15",
alpha = 0.8)
graphics.off()
plotMA(res_con_uvb_week15,
main = "Control vs. UVB at Week 15",
alpha = 0.8)
res_sfn_uvb_week15 <- results(dds,
contrast = c(0,0,0,0,1,0,0,1,0),
alpha = 0.1)
res_sfn_uvb_week15 <- res_sfn_uvb_week15[order(res_sfn_uvb_week15$padj,
decreasing = FALSE),]
summary(res_sfn_uvb_week15)
out of 17202 with nonzero total read count
adjusted p-value < 0.1
LFC > 0 (up) : 20, 0.12%
LFC < 0 (down) : 10, 0.058%
outliers [1] : 0, 0%
low counts [2] : 7004, 41%
(mean count < 53)
[1] see 'cooksCutoff' argument of ?results
[2] see 'independentFiltering' argument of ?results
# out of 17202 with nonzero total read count
# adjusted p-value < 0.1
# LFC > 0 (up) : 20, 0.12%
# LFC < 0 (down) : 10, 0.058%
# outliers [1] : 0, 0%
# low counts [2] : 7004, 41%
# (mean count < 53)
# How many adjusted p-values were less than 0.05?
sum(res_sfn_uvb_week15$padj < 0.1,
na.rm = TRUE)
[1] 30
# 30
# NOT THE SAME AS!!!:
res_sfn_uvb_week15.1 <- results(dds,
contrast = list("trt_SFN_vs_UVB",
"time15w.trtSFN"),
alpha = 0.1)
res_sfn_uvb_week15.1 <- res_sfn_uvb_week15.1[order(res_sfn_uvb_week15.1$padj,
decreasing = FALSE),]
summary(res_sfn_uvb_week15.1)
out of 17202 with nonzero total read count
adjusted p-value < 0.1
LFC > 0 (up) : 14, 0.081%
LFC < 0 (down) : 24, 0.14%
outliers [1] : 0, 0%
low counts [2] : 3335, 19%
(mean count < 4)
[1] see 'cooksCutoff' argument of ?results
[2] see 'independentFiltering' argument of ?results
# out of 17202 with nonzero total read count
# adjusted p-value < 0.1
# LFC > 0 (up) : 14, 0.081%
# LFC < 0 (down) : 24, 0.14%
# outliers [1] : 0, 0%
# low counts [2] : 3335, 19%
# (mean count < 4)
# How many adjusted p-values were less than 0.05?
sum(res_sfn_uvb_week15.1$padj < 0.1,
na.rm = TRUE)
[1] 38
# 38
# MA plot
# Save for publication
tiff(filename = "tmp/ma_w2_sfn_uvb.tiff",
height = 6,
width = 7,
units = 'in',
res = 600,
compression = "lzw+p")
print(plotMA(res_sfn_uvb_week15,
main = "UVB+SFN vs UVB at Week 15",
alpha = 0.8))
NULL
graphics.off()
print(plotMA(res_sfn_uvb_week15,
main = "UVB+SFN vs UVB at Week 15",
alpha = 0.8))
NULL
lgene.w15.con <- unique(res_con_uvb_week15@rownames[res_con_uvb_week15$padj < 0.1])
lgene.w15.sfn <- unique(res_sfn_uvb_week15@rownames[res_sfn_uvb_week15$padj < 0.1])
lgene.w15 <- lgene.w15.con[lgene.w15.con %in% lgene.w15.sfn]
lgene.w15 <- lgene.w15 [!is.na(lgene.w15 )]
length(unique(lgene.w15))
[1] 15
Plot of DESeq-normalizedcounts of genes significant in both comparisons at Week 15:
# Get the DESeq-normalize counts
dp1 <- list()
for (i in 1:length(lgene.w15)) {
out <- plotCounts(dds,
gene = lgene.w15[[i]],
intgroup = c("trt",
"time"),
returnData = TRUE)
dp1[[i]] <- data.table(Geneid = lgene.w15[[i]],
Sample = rownames(out),
out)
}
dp1 <- rbindlist(dp1)
dp1$trt <- factor(dp1$trt,
levels = c("CON",
"UVB",
"SFN"))
dp1$time <- factor(dp1$time,
levels = c("02w",
"15w",
"25w"),
labels = c("Week 2",
"Week 15",
"Week 25"))
dp1$Geneid <- factor(dp1$Geneid,
levels = lgene.w15)
dp1[, mu := mean(count,
na.rm = TRUE),
by = c("Geneid",
"trt",
"time")]
dmu <- unique(dp1[, -c("Sample",
"count")])
datatable(head(dmu),
rownames = FALSE,
class = "cell-border stripe") %>%
formatRound(columns = 4,
digits = 2)
List of 1
$ axis.text.x:List of 11
..$ family : NULL
..$ face : NULL
..$ colour : NULL
..$ size : NULL
..$ hjust : num 1
..$ vjust : NULL
..$ angle : num 45
..$ lineheight : NULL
..$ margin : NULL
..$ debug : NULL
..$ inherit.blank: logi FALSE
..- attr(*, "class")= chr [1:2] "element_text" "element"
- attr(*, "class")= chr [1:2] "theme" "gg"
- attr(*, "complete")= logi FALSE
- attr(*, "validate")= logi TRUE
dp1.tmp <- dp1[dp1$Geneid %in% unique(dmu.w15$Geneid[dmu.w15$up.dn]), ]
dmu.tmp <- dmu[dmu$Geneid %in% unique(dmu.w15$Geneid[dmu.w15$up.dn]), ]
p1 <- ggplot(dp1.tmp,
aes(x = time,
y = count,
group = trt,
fill = trt)) +
facet_wrap(~ Geneid,
scale = "free_y") +
geom_point(position = position_dodge(0.5),
shape = 21,
size = 5,
color = "black") +
geom_line(data = dmu.tmp,
aes(x = time,
y = mu,
group = trt,
colour = trt),
position = position_dodge(0.5),
alpha = 0.5,
size = 2) +
scale_x_discrete("") +
scale_y_continuous("DESeq-Normalized Counts") +
scale_fill_discrete("Treatment")
print(p1)
List of 1
$ axis.text.x:List of 11
..$ family : NULL
..$ face : NULL
..$ colour : NULL
..$ size : NULL
..$ hjust : num 1
..$ vjust : NULL
..$ angle : num 45
..$ lineheight : NULL
..$ margin : NULL
..$ debug : NULL
..$ inherit.blank: logi FALSE
..- attr(*, "class")= chr [1:2] "element_text" "element"
- attr(*, "class")= chr [1:2] "theme" "gg"
- attr(*, "complete")= logi FALSE
- attr(*, "validate")= logi TRUE
dp1.tmp <- dp1[dp1$Geneid %in% unique(dmu.w15$Geneid[dmu.w15$dn.up]), ]
dmu.tmp <- dmu[dmu$Geneid %in% unique(dmu.w15$Geneid[dmu.w15$dn.up]), ]
p1 <- ggplot(dp1.tmp,
aes(x = time,
y = count,
group = trt,
fill = trt)) +
facet_wrap(~ Geneid,
scale = "free_y") +
geom_point(position = position_dodge(0.5),
shape = 21,
size = 5,
color = "black") +
geom_line(data = dmu.tmp,
aes(x = time,
y = mu,
group = trt,
colour = trt),
position = position_dodge(0.5),
alpha = 0.5,
size = 2) +
scale_x_discrete("") +
scale_y_continuous("DESeq-Normalized Counts") +
scale_fill_discrete("Treatment")
print(p1)
up.dn.w15 <- unique(as.character(dmu.w15$Geneid[dmu.w15$up.dn]))
dn.up.w15 <- unique(as.character(dmu.w15$Geneid[dmu.w15$dn.up]))
ll <- unique(c(up.dn.w15,
dn.up.w15))
# 16 genes
con_uvb_week15 <- data.table(Geneid = res_con_uvb_week15@rownames,
log2FoldChange = res_con_uvb_week15@listData$log2FoldChange)
sfn_uvb_week15 <- data.table(Geneid = res_sfn_uvb_week15@rownames,
log2FoldChange = -res_sfn_uvb_week15@listData$log2FoldChange)
t1 <- merge(con_uvb_week15[con_uvb_week15$Geneid %in% ll, ],
sfn_uvb_week15[sfn_uvb_week15$Geneid %in% ll, ],
by = "Geneid")
colnames(t1)[2:3] <- c("Control vs. UVB",
"UVB vs. SFN+UVB")
t1 <- t1[order(t1$`Control vs. UVB`,
decreasing = TRUE), ]
write.csv(t1,
file = "tmp/w15_sign_changes.csv",
row.names = FALSE)
ll <- melt.data.table(data = t1,
id.vars = 1,
measure.vars = 2:3,
variable.name = "Comparison",
value.name = "Gene Expression Diff")
ll$Comparison <- factor(ll$Comparison,
levels = c("Control vs. UVB",
"UVB vs. SFN+UVB"))
lvls <- ll[ll$Comparison == "Control vs. UVB", ]
ll$Geneid <- factor(ll$Geneid,
levels = lvls$Geneid[order(lvls$`Gene Expression Diff`)])
# Add dendrogram----
dt.dndr <- data.frame(t1[Geneid %in% levels(ll$Geneid), ])
rownames(dt.dndr) <- dt.dndr$Gene
dt.dndr <- dt.dndr[, -1]
# Compute distances between genes----
sampleDists <- dist(dt.dndr)
# Make dendrogram data----
dhc <- as.dendrogram(hclust(d = sampleDists),
horiz = TRUE)
ddata <- dendro_data(dhc,
type = "rectangle")
# Segment data----
dtp1 <- segment(ddata)
# Hitmap data----
dtp2 <- ll
dtp2$Geneid <- factor(dtp2$Geneid,
levels = ddata$labels$label)
offset.size <- 4
p1 <- ggplot(data = dtp2) +
coord_polar("y",
start = -0.3,
direction = -1) +
geom_tile(aes(x = as.numeric(Comparison),
y = Geneid,
fill = `Gene Expression Diff`),
color = "white") +
geom_text(data = dtp2[Comparison == "Control vs. UVB", ],
aes(x = rep(1.75,
nlevels(Geneid)),
y = Geneid,
angle = 90 + seq(from = 90,
to = 330,
length.out = nlevels(Geneid))[as.numeric(Geneid)] +
offset.size,
label = unique(Geneid)),
hjust = 0) +
geom_text(data = dtp2[Geneid == levels(dtp2$Geneid)[1], ],
aes(x = 1:nlevels(Comparison),
y = rep(-offset.size,
nlevels(Comparison)),
angle = 0,
label = levels(Comparison)),
hjust = 1,
size = 5) +
scale_fill_gradient2(low = "red",
high = "green",
mid = "grey",
midpoint = 0,
name = "") +
scale_y_discrete("",
expand = c(0, 0)) +
theme(plot.title = element_text(hjust = 0.5),
axis.title.x = element_blank(),
axis.text.x = element_blank(),
axis.ticks.x = element_blank(),
axis.title.y = element_blank(),
axis.text.y = element_blank(),
axis.ticks.y = element_blank(),
panel.background = element_blank(),
legend.position = "bottom",
legend.text = element_text(size = 15),
legend.direction = "horizontal",
legend.key.width = unit(1, "in"),
legend.key.height = unit(0.3, "in")) +
geom_segment(data = dtp1,
aes(x = -sqrt(y) + 0.5,
y = x,
xend = -sqrt(yend) + 0.5,
yend = xend),
size = 1)
tiff(filename = "tmp/skin_ubv_w15_sfn_hitmap_with_phylo.tiff",
height = 8,
width = 8,
units = 'in',
res = 600,
compression = "lzw+p")
plot(p1)
graphics.off()
print(p1)
# out of 17202 with nonzero total read count
# 1. Ctrl vs. UVB
# adjusted p-value < 0.1
# LFC > 0 (up) : 1513, 8.8%
# LFC < 0 (down) : 1463, 8.5%
# 2 genes down-up-down
# 2. SFN+UVB vs. UVB
# adjusted p-value < 0.1
# LFC > 0 (up) : 20, 0.12%
# LFC < 0 (down) : 10, 0.058%
# 9 gens up-down-up
p1 <- ggplot() +
geom_circle(aes(x0 = c(1, 2, 1, 2),
y0 = c(1, 1, 4, 4),
r = rep(1, 4),
color = factor(c(2, 1, 1, 2))),
size = 2) +
geom_text(aes(x = rep(c(0.5, 1.5, 2.5), 2),
y = rep(c(1, 4), each = 3),
label = format(c(20, 9, 10, 1513, 2, 1463),
big.mark = ","))) +
scale_color_manual(values = c("green", "red")) +
theme_void() +
theme(legend.position = "none")
tiff(filename = "tmp/skin_ubv_sfn_w2_venn.tiff",
height = 6,
width = 4,
units = 'in',
res = 600,
compression = "lzw+p")
plot(p1)
graphics.off()
print(p1)
Tests if the effect of NOT treating with UVB vs. treating with UVB is different at Week 15 compared to Week 2:
res_int_con_uvb_week <- results(dds,
name = "time15w.trtCON",
alpha = 0.1)
res_int_con_uvb_week <- res_int_con_uvb_week[order(res_int_con_uvb_week$padj,
decreasing = FALSE),]
print(res_int_con_uvb_week)
summary(res_int_con_uvb_week)
# How many adjusted p-values were less than 0.05?
sum(res_int_con_uvb_week$padj < 0.1,
na.rm = TRUE)
# MA plot
print(plotMA(res_int_con_uvb_week,
main = "(Control vs. UVB) x TIme Interaction",
alpha = 0.9))
Tests if the effect of treating with UVB+SFN vs. treating with UVB is different at Week 15 compared to Week 2:
res_int_sfn_uvb_week <- results(dds,
name = "time15w.trtSFN",
alpha = 0.1)
res_int_sfn_uvb_week <- res_int_sfn_uvb_week[order(res_int_sfn_uvb_week$padj,
decreasing = FALSE),]
print(res_int_sfn_uvb_week)
summary(res_int_sfn_uvb_week)
# How many adjusted p-values were less than 0.05?
sum(res_int_sfn_uvb_week$padj < 0.1,
na.rm = TRUE)
# MA plot
print(plotMA(res_int_sfn_uvb_week))
# NOTE: same as
# res <- results(dds,
# alpha = 0.05)
# res <- res[order(res$padj, decreasing = FALSE),]
# res
NOTE: By default, the results(dds)* prints the results for the last level of the last term, i.e. here it was for for the interaction term SFN vs. UVB at Week 15 vs. Week 2.
lgene.con <- unique(res_int_con_uvb_week@rownames[res_int_con_uvb_week$padj < 0.1])
lgene.sfn <- unique(res_int_sfn_uvb_week@rownames[res_int_sfn_uvb_week$padj < 0.1])
lgene <- lgene.con[lgene.con %in% lgene.sfn]
lgene <- lgene[!is.na(lgene)]
lgene
Plot of DESeq-normalizedcounts of genes with smallest adjusted p-value for the interaction term:
# Get the DESeq-normalize counts
dp1 <- list()
for (i in 1:length(lgene)) {
out <- plotCounts(dds,
gene = lgene[[i]],
intgroup = c("trt",
"time"),
returnData = TRUE)
dp1[[i]] <- data.table(Geneid = lgene[[i]],
Sample = rownames(out),
out)
}
dp1 <- rbindlist(dp1)
dp1$trt <- factor(dp1$trt,
levels = c("CON",
"UVB",
"SFN"))
dp1$time <- factor(dp1$time,
levels = c("02w",
"15w"),
labels = c("Week 2",
"Week 15"))
dp1$Geneid <- factor(dp1$Geneid,
levels = lgene)
dp1[, mu := mean(count,
na.rm = TRUE),
by = c("Geneid",
"trt",
"time")]
dmu <- unique(dp1[, -c("Sample",
"count")])
p1 <- ggplot(dp1,
aes(x = time,
y = count,
group = trt,
fill = trt)) +
facet_wrap(~ Geneid,
scale = "free_y") +
geom_point(position = position_dodge(0.5),
shape = 21,
size = 5,
color = "black") +
geom_line(data = dmu,
aes(x = time,
y = mu,
group = trt,
colour = trt),
position = position_dodge(0.5),
alpha = 0.5,
size = 2) +
scale_x_discrete("") +
scale_y_continuous("DESeq-Normalized Counts") +
scale_fill_discrete("Treatment")
print(p1)
Compare to the plot of TPM-normalizedcounts of genes with smallest adjusted p-value for the interaction term:
# Examine TPM values for the same genes
tmp <- tpm[Geneid %in% lgene, ]
tmp$Geneid <- factor(tmp$Geneid,
levels = lgene)
tmp <- melt.data.table(data = tmp,
id.vars = 1,
measure.vars = 3:ncol(tmp),
variable.name = "Sample",
value.name = "TPM")
tmp <- merge(dmeta,
tmp,
by = "Sample")
p1 <- ggplot(tmp,
aes(x = Week,
y = TPM,
fill = Treatment,
group = Treatment)) +
facet_wrap(~ Geneid,
scales = "free_y") +
geom_point(position = position_dodge(0.5),
shape = 21,
size = 5,
color = "black")+
scale_x_discrete("")
plot(p1)
sessionInfo()